Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8023
    Prev
    Next
    INDEX
    Explanations

    No. followed by identifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    พ
    -0.87
    nmgp
    -0.87
     Politik
    -0.79
    أ
    -0.73
     optical
    -0.72
    sparse
    -0.71
     Optical
    -0.70
    オ
    -0.70
    প
    -0.69
     Oliver
    -0.69
    POSITIVE LOGITS
     Forst
    0.76
     spô
    0.70
    Bril
    0.69
    firstName
    0.68
    Feng
    0.67
     shimmer
    0.66
     Tất
    0.66
    ȴ
    0.66
    GIVEREF
    0.66
     bây
    0.65
    Activations Density 0.502%

    No Known Activations